MIT AI Risk Repository · Risk Category · 57.03.00

Contextual Hazards

Open the MIT Risk Navigator All entries from Ghosh2024

Description

"Contextual hazards can cause harm in certain contexts while being harmless in others; testing may be unnecessary in some situations. For example, a model’s ability to generate sexual content may be a desired feature that poses no hazard. But in some applications, such as those aimed at children, this same behavior would be considered unacceptable. In cases where a particular contextual hazard is relevant to the application, assessment-standard implementers could exclude that category. This ability to turn off contextual hazards is an example of the standard’s flexibility, which we discuss bel

From AILUMINATE: Introducing v1.0 of the AI Risk and Reliability Benchmark from MLCommons (Ghosh2024), as extracted by the MIT AI Risk Repository (CC BY 4.0).

Classification

Domain: 1. Discrimination & Toxicity
Subdomain: 1.2 Exposure to toxic content
Causal entity: AI
Intent: Other
Timing: Post-deployment

Subdomain definition: AI exposing users to harmful, abusive, unsafe or inappropriate content. May involve AI creating, describing, providing advice, or encouraging action. Examples of toxic content include hate-speech, violence, extremism, illegal acts, child sexual abuse material, as well as content that violates community norms such as profanity, inflammatory political speech, or pornography.

Real-world incidents in this subdomain

Browse all incidents in this subdomain

How other frameworks describe this risk

Harmful Content
Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems (Cui2024)
Toxicity
Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems (Cui2024)
Toxic Training Data
Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems (Cui2024)
Not-Suitable-for-Work (NSFW) Prompts
Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems (Cui2024)
Controversial Opinions
Towards Safer Generative Language Models: A Survey on Safety Risks, Evaluations, and Improvements (Deng2023)
Toxicity and Abusive Content
Towards Safer Generative Language Models: A Survey on Safety Risks, Evaluations, and Improvements (Deng2023)
Harmful responses
Future Risks of Frontier AI (GOS2023)
Violation of social norms
The Ethics of Advanced AI Assistants (Gabriel2024)

Other entries from Ghosh2024

Physical Hazards Risk Category
Violent Crimes Risk Sub-Category · 1.2
Sex-Related Crimes Risk Sub-Category · 1.2
Suicide & Self-Harm Risk Sub-Category · 1.2
Indiscriminate Weapons (CBRNE) Risk Sub-Category · 4.2
Child Sexual Exploitation Risk Sub-Category · 1.2
Nonphysical Hazards Risk Category
Intellectual Property Risk Sub-Category · 6.3
Defamation Risk Sub-Category · 3.1
Hate Risk Sub-Category · 1.2
Nonviolent Crimes Risk Sub-Category · 1.2
Privacy Risk Sub-Category · 2.1